{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OXHPOGYUQDN25GK3NWENNNJ7JA","short_pith_number":"pith:OXHPOGYU","schema_version":"1.0","canonical_sha256":"75cef71b1480dbae995b6d88d6b53f48213462b63d8c13c9b1bf25d3fa7f4d6f","source":{"kind":"arxiv","id":"2508.12966","version":1},"attestation_state":"computed","paper":{"title":"GazeDETR: Gaze Detection using Disentangled Head and Gaze Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arcot Sowmya, Gelareh Mohammadi, Ryan Anthony Jalova de Belen","submitted_at":"2025-08-18T14:41:18Z","abstract_excerpt":"Gaze communication plays a crucial role in daily social interactions. Quantifying this behavior can help in human-computer interaction and digital phenotyping. While end-to-end models exist for gaze target detection, they only utilize a single decoder to simultaneously localize human heads and predict their corresponding gaze (e.g., 2D points or heatmap) in a scene. This multitask learning approach generates a unified and entangled representation for human head localization and gaze location prediction. Herein, we propose GazeDETR, a novel end-to-end architecture with two disentangled decoders"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.12966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T14:41:18Z","cross_cats_sorted":[],"title_canon_sha256":"12452606926650d137fa3c5476fcaea431f374089a2219850e1f031906df9b3d","abstract_canon_sha256":"ebe9ca4756962c03d6bf27d47a985d952d5db607cf3c33bd306b5d9d7ac91e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:30.000585Z","signature_b64":"/5eJbqWLGscx7f6BcOvsShRtyBSc2+q8CHOsKpZr2twLHvwMneSOOSEADQUpyIQZiU1g4Ejl2LnOtEdr9xt/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75cef71b1480dbae995b6d88d6b53f48213462b63d8c13c9b1bf25d3fa7f4d6f","last_reissued_at":"2026-07-05T11:55:30.000131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:30.000131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GazeDETR: Gaze Detection using Disentangled Head and Gaze Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arcot Sowmya, Gelareh Mohammadi, Ryan Anthony Jalova de Belen","submitted_at":"2025-08-18T14:41:18Z","abstract_excerpt":"Gaze communication plays a crucial role in daily social interactions. Quantifying this behavior can help in human-computer interaction and digital phenotyping. While end-to-end models exist for gaze target detection, they only utilize a single decoder to simultaneously localize human heads and predict their corresponding gaze (e.g., 2D points or heatmap) in a scene. This multitask learning approach generates a unified and entangled representation for human head localization and gaze location prediction. Herein, we propose GazeDETR, a novel end-to-end architecture with two disentangled decoders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12966","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.12966/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.12966","created_at":"2026-07-05T11:55:30.000187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12966v1","created_at":"2026-07-05T11:55:30.000187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12966","created_at":"2026-07-05T11:55:30.000187+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXHPOGYUQDN2","created_at":"2026-07-05T11:55:30.000187+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXHPOGYUQDN25GK3","created_at":"2026-07-05T11:55:30.000187+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXHPOGYU","created_at":"2026-07-05T11:55:30.000187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA","json":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA.json","graph_json":"https://pith.science/api/pith-number/OXHPOGYUQDN25GK3NWENNNJ7JA/graph.json","events_json":"https://pith.science/api/pith-number/OXHPOGYUQDN25GK3NWENNNJ7JA/events.json","paper":"https://pith.science/paper/OXHPOGYU"},"agent_actions":{"view_html":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA","download_json":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA.json","view_paper":"https://pith.science/paper/OXHPOGYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12966&json=true","fetch_graph":"https://pith.science/api/pith-number/OXHPOGYUQDN25GK3NWENNNJ7JA/graph.json","fetch_events":"https://pith.science/api/pith-number/OXHPOGYUQDN25GK3NWENNNJ7JA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA/action/storage_attestation","attest_author":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA/action/author_attestation","sign_citation":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA/action/citation_signature","submit_replication":"https://pith.science/pith/OXHPOGYUQDN25GK3NWENNNJ7JA/action/replication_record"}},"created_at":"2026-07-05T11:55:30.000187+00:00","updated_at":"2026-07-05T11:55:30.000187+00:00"}